Dynamic Changes of Population Size in Training of Artificial Neural Networks

被引:0
|
作者
Slowik, A. [1 ]
Bialko, M. [1 ]
机构
[1] Koszalin Univ Technol, Dept Elect & Comp Sci, Koszalin, Poland
来源
HUMAN-COMPUTER SYSTEMS INTERACTION: BACKGROUNDS AND APPLICATIONS | 2009年 / 60卷
关键词
DIFFERENTIAL EVOLUTION ALGORITHM; GLOBAL OPTIMIZATION;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper an adaptive differential evolution algorithm with dynamic changes of population size is presented. In proposed algorithm an adaptive selection of control parameters of the algorithm are introduced. Due to these parameters selection, the algorithm gives better results than differential evolution algorithm without this modification. Also, in presented algorithm dynamic changes of population size are introduced. This modification try to overcome limitations connected with premature convergence of the algorithm. Due to dynamic changes of population size, the algorithm can easier get out from local minimum. The proposed algorithm is used to train artificial neural networks. Results obtained are compared with those obtained using: adaptive differential evolution algorithm without dynamic changes of population size, method based on evolutionary algorithm, error back-propagation algorithm, and Levenberg-Marquardt algorithm.
引用
收藏
页码:517 / 527
页数:11
相关论文
共 50 条
  • [21] Artificial neural networks as a tool of modeling of training loads
    Rygula, I
    MODELLING AND CONTROL IN BIOMEDICAL SYSTEMS 2003 (INCLUDING BIOLOGICAL SYSTEMS), 2003, : 531 - 535
  • [22] Efficient Training of Artificial Neural Networks for Autonomous Navigation
    Pomerleau, Dean A.
    NEURAL COMPUTATION, 1991, 3 (01) : 88 - 97
  • [23] Evolutionary Artificial Bee Colony for Neural Networks Training
    Ribeiro Serra Neto, Mario Tasso
    Florenzano Mollinetti, Marco Antonio
    Pereira, Rodrigo Lisboa
    2017 13TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (ICNC-FSKD), 2017, : 44 - 49
  • [24] Physics solves a training problem for artificial neural networks
    Damien Querlioz
    Nature, 2024, 632 (8024) : 264 - 265
  • [25] Training artificial neural networks to perform rainfall disaggregation
    Burian, SJ
    Durrans, SR
    Nix, SJ
    Pitt, RE
    JOURNAL OF HYDROLOGIC ENGINEERING, 2001, 6 (01) : 43 - 51
  • [26] COOT optimization algorithm on training artificial neural networks
    Ozden, Aysenur
    Iseri, Ismail
    KNOWLEDGE AND INFORMATION SYSTEMS, 2023, 65 (08) : 3353 - 3383
  • [27] Training and application of artificial neural networks with incomplete data
    Viharos, ZJ
    Monostori, L
    Vincze, T
    DEVELOPMENTS IN APPLIED ARTIFICAIL INTELLIGENCE, PROCEEDINGS, 2002, 2358 : 649 - 659
  • [28] Training artificial neural networks using Taguchi methods
    MacLeod, C
    Dror, G
    Maxwell, G
    ARTIFICIAL INTELLIGENCE REVIEW, 1999, 13 (03) : 177 - 184
  • [29] Artificial neural networks as a tool of modeling of training loads
    Rygula, Igor
    2005 27TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-7, 2005, : 2985 - 2988
  • [30] Training Artificial Neural Networks Using Taguchi Methods
    Chris Macleod
    Geva Dror
    Grant Maxwell
    Artificial Intelligence Review, 1999, 13 : 177 - 184